© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196344
    Prev
    Next
    INDEX
    Explanations

    pragmatic view, dual methods, nature documentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    1.14
    to
    0.96
    1
    0.94
    af
    0.89
    is
    0.84
    and
    0.82
    new
    0.79
    tl
    0.79
    Ö
    0.78
    l
    0.77
    POSITIVE LOGITS
    cita
    0.81
    وون
    0.70
    SpriteCollision
    0.70
    ين
    0.70
    드시
    0.68
     underdeveloped
    0.67
    ıştır
    0.66
    يكل
    0.66
    ీ
    0.66
     ابراہیم
    0.65
    Activations Density 0.000%

    No Known Activations